© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102988
    Prev
    Next
    INDEX
    Explanations

    freedom of speech

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on mentions of “freedom of…” or closely related rights‐type phrases (e.g. freedom of speech, freedom of association).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amérique
    -0.97
     Etiquette
    -0.86
     lounges
    -0.85
    encephal
    -0.83
     salomon
    -0.83
    隐隐
    -0.81
     Decoder
    -0.78
    oad
    -0.77
     يل
    -0.76
     Bracelets
    -0.76
    POSITIVE LOGITS
     speech
    3.11
    speech
    2.52
     expression
    2.31
     Speech
    2.31
    Speech
    2.13
    expression
    1.81
     Expression
    1.72
     freedom
    1.71
     SPEECH
    1.65
    Expression
    1.57
    Activations Density 0.048%

    No Known Activations